{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KGHZM6TGLZNXYI2WGX66GZDMMQ","short_pith_number":"pith:KGHZM6TG","schema_version":"1.0","canonical_sha256":"518f967a665e5b7c235635fde3646c643a14ecfa42cf11531bd240a1900fc12e","source":{"kind":"arxiv","id":"2202.03397","version":4},"attestation_state":"computed","paper":{"title":"Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Massimiliano Pontil, Riccardo Grazzi, Saverio Salzo","submitted_at":"2022-02-07T18:35:46Z","abstract_excerpt":"We analyse a general class of bilevel problems, in which the upper-level problem consists in the minimization of a smooth objective function and the lower-level problem is to find the fixed point of a smooth contraction map. This type of problems include instances of meta-learning, equilibrium models, hyperparameter optimization and data poisoning adversarial attacks. Several recent works have proposed algorithms which warm-start the lower-level problem, i.e.~they use the previous lower-level approximate solution as a staring point for the lower-level solver. This warm-start procedure allows o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.03397","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-02-07T18:35:46Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"941f37feac0f6061a7251601a222182dd28be8d6a001cc3f4f7ed19450b2c6a1","abstract_canon_sha256":"10166aa01501d87736d8d02cea39b2248036f1413c43586dce15317aae29124d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:18.888793Z","signature_b64":"dYmoq/gEJCDxv/IzLi/WYNpM/Rma6fZ/8mOOmx+rhUOEL6WtL9COtGfBJw8WNJOsXb+JkUM0xtVLm90WlrCsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"518f967a665e5b7c235635fde3646c643a14ecfa42cf11531bd240a1900fc12e","last_reissued_at":"2026-07-05T07:13:18.888300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:18.888300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Massimiliano Pontil, Riccardo Grazzi, Saverio Salzo","submitted_at":"2022-02-07T18:35:46Z","abstract_excerpt":"We analyse a general class of bilevel problems, in which the upper-level problem consists in the minimization of a smooth objective function and the lower-level problem is to find the fixed point of a smooth contraction map. This type of problems include instances of meta-learning, equilibrium models, hyperparameter optimization and data poisoning adversarial attacks. Several recent works have proposed algorithms which warm-start the lower-level problem, i.e.~they use the previous lower-level approximate solution as a staring point for the lower-level solver. This warm-start procedure allows o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03397","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.03397/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.03397","created_at":"2026-07-05T07:13:18.888367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03397v4","created_at":"2026-07-05T07:13:18.888367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03397","created_at":"2026-07-05T07:13:18.888367+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGHZM6TGLZNX","created_at":"2026-07-05T07:13:18.888367+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGHZM6TGLZNXYI2W","created_at":"2026-07-05T07:13:18.888367+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGHZM6TG","created_at":"2026-07-05T07:13:18.888367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20017","citing_title":"A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ","json":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ.json","graph_json":"https://pith.science/api/pith-number/KGHZM6TGLZNXYI2WGX66GZDMMQ/graph.json","events_json":"https://pith.science/api/pith-number/KGHZM6TGLZNXYI2WGX66GZDMMQ/events.json","paper":"https://pith.science/paper/KGHZM6TG"},"agent_actions":{"view_html":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ","download_json":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ.json","view_paper":"https://pith.science/paper/KGHZM6TG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03397&json=true","fetch_graph":"https://pith.science/api/pith-number/KGHZM6TGLZNXYI2WGX66GZDMMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KGHZM6TGLZNXYI2WGX66GZDMMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ/action/storage_attestation","attest_author":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ/action/author_attestation","sign_citation":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ/action/citation_signature","submit_replication":"https://pith.science/pith/KGHZM6TGLZNXYI2WGX66GZDMMQ/action/replication_record"}},"created_at":"2026-07-05T07:13:18.888367+00:00","updated_at":"2026-07-05T07:13:18.888367+00:00"}